{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T16:16:25Z","timestamp":1771949785626,"version":"3.50.1"},"reference-count":73,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"State Key Research and Development Program","award":["2016YFB1001003"],"award-info":[{"award-number":["2016YFB1001003"]}]},{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"crossref","award":["U1611461"],"award-info":[{"award-number":["U1611461"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"crossref","award":["61502301"],"award-info":[{"award-number":["61502301"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"crossref","award":["61527804"],"award-info":[{"award-number":["61527804"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"crossref","award":["61521062"],"award-info":[{"award-number":["61521062"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"China's Thousand Youth Talents Plan, STCSM","award":["18DZ1112300"],"award-info":[{"award-number":["18DZ1112300"]}]},{"name":"China's Thousand Youth Talents Plan, STCSM","award":["17511105401"],"award-info":[{"award-number":["17511105401"]}]},{"name":"China's Thousand Youth Talents Plan, STCSM","award":["18DZ2270700"],"award-info":[{"award-number":["18DZ2270700"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2019,7]]},"DOI":"10.1109\/tmm.2018.2885235","type":"journal-article","created":{"date-parts":[[2018,12,7]],"date-time":"2018-12-07T00:02:15Z","timestamp":1544140935000},"page":"1799-1812","source":"Crossref","is-referenced-by-count":15,"title":["Structure-Constrained Motion Sequence Generation"],"prefix":"10.1109","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3209-8965","authenticated-orcid":false,"given":"Yichao","family":"Yan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7339-028X","authenticated-orcid":false,"given":"Bingbing","family":"Ni","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9837-8930","authenticated-orcid":false,"given":"Wendong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingwei","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaokang","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123277"},{"key":"ref72","article-title":"Openface: A general-purpose face recognition library with mobile applications","author":"amos","year":"2016"},{"key":"ref71","first-page":"2234","article-title":"Improved techniques for training GANs","author":"salimans","year":"0","journal-title":"Proc 30th Int Conf Neural Inf Process Syst"},{"key":"ref70","first-page":"4417","article-title":"Unsupervised learning of disentangled representations from video","author":"denton","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2006.08.004"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2002.1044791"},{"key":"ref33","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1109\/TSMCC.2009.2027608","article-title":"Advances in view-invariant human motion analysis: A review","volume":"40","author":"ji","year":"2010","journal-title":"IEEE Trans Syst Man Cybern Part C"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2006.10.016"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2012.6239234"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2005.1521424"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2006.07.010"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/AFGR.1996.557241"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.1980.6447705"},{"key":"ref34","first-page":"820","article-title":"Bayesian reconstruction of 3D human motion from single-camera video.","volume":"99","author":"howe","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00165"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_23"},{"key":"ref61","first-page":"4417","article-title":"Unsupervised learning of disentangled representations from video","author":"denton","year":"2017","journal-title":"Neural Inf Process Syst"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2004.1334462"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.264"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_43"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.267"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.248"},{"key":"ref66","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014"},{"key":"ref67","article-title":"Tensorflow: Large-scale machine learning on heterogeneous distributed systems","author":"abadi","year":"2016"},{"key":"ref68","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref69","article-title":"Decomposing motion and content for natural video sequence prediction","author":"villegas","year":"0"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_47"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.316"},{"key":"ref21","article-title":"Unsupervised representation learning with deep convolutional generative adversarial networks","author":"radford","year":"2015"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.18"},{"key":"ref26","article-title":"Conditional generative adversarial nets","author":"mirza","year":"2014"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1023\/A:1026553619983"},{"key":"ref51","first-page":"1462","article-title":"DRAW: A recurrent neural network for image generation","author":"gregor","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref59","first-page":"91","article-title":"Visual dynamics: Probabilistic future frame synthesis via cross convolutional networks","author":"xue","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/2461912.2461950"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/1186822.1073268"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/344779.345012"},{"key":"ref55","article-title":"Wasserstein GAN","author":"arjovsky","year":"2017"},{"key":"ref54","article-title":"Loss-sensitive generative adversarial networks on Lipschitz densities","author":"qi","year":"2017"},{"key":"ref53","first-page":"2172","article-title":"Infogan: Interpretable representation learning by information maximizing generative adversarial nets","author":"chen","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref52","article-title":"Energy-based generative adversarial network","author":"zhao","year":"2016"},{"key":"ref10","first-page":"2863","article-title":"Action-conditional video prediction using deep networks in Atari games","author":"oh","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref11","article-title":"Deep predictive coding networks for video prediction and unsupervised learning","author":"lotter","year":"2016"},{"key":"ref40","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1023\/A:1023012723347","article-title":"Human body model acquisition and tracking using voxel data","volume":"53","author":"miki?","year":"2003","journal-title":"Int J Comput Vision"},{"key":"ref12","article-title":"Deep multi-scale video prediction beyond mean square error","author":"mathieu","year":"2015"},{"key":"ref13","article-title":"Transformation-based models of video sequences","author":"van amersfoort","year":"2017"},{"key":"ref14","article-title":"Video (language) modeling: A baseline for generative models of natural videos","author":"ranzato","year":"2014"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_51"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.143"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2016.7477553"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.388"},{"key":"ref19","first-page":"3560","article-title":"Learning to generate long-term future via hierarchical prediction","author":"villegas","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2599174"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806222"},{"key":"ref6","article-title":"Auto-encoding variational Bayes","author":"kingma","year":"2013"},{"key":"ref5","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref8","first-page":"64","article-title":"Unsupervised learning for physical interaction through video prediction","author":"finn","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2762010"},{"key":"ref7","first-page":"843","article-title":"Unsupervised learning of video representations using LSTMS","author":"srivastava","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref9","first-page":"613","article-title":"Generating videos with scene dynamics","author":"vondrick","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.244"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2617079"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.214"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.471"},{"key":"ref42","first-page":"1110","article-title":"Hierarchical recurrent neural network for skeleton based action recognition","author":"du","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2749159"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2674622"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2758524"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/8743377\/08565937.pdf?arnumber=8565937","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T20:50:18Z","timestamp":1657745418000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8565937\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7]]},"references-count":73,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2018.2885235","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,7]]}}}